Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Modeling drug mechanism of action with large scale gene-expression profiles using GPAR, an artificial intelligence platform

Fig. 1

a Drugs prediction: user/pre-defined one or multiple drugs would be taken as positive samples in model training. And the predicted compound rank lists, AUROC of prediction model and visualizations of both training and predicted data would be returned. b MOA prediction: 83 MOA prediction models with AUROC ≥ 0.6 were used to predict the potential MOA of user uploaded or selected expression profiles. And the top 10 predicted MOAs would be presented. c The AUROC of GSEA and GPAR by calculating 103 MOAs. AUROC of GPAR is significantly higher than that of GSEA (Wilcoxon matched-pairs signed rank test, p < 0.0001). d Comparison of trained model performance of estrogen receptor agonists in PC3 and A549 (orange) cell lines and in MCF7 and HT29 (blue) cell lines

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us